SmolLM2-135M — 1BP format

HuggingFaceTB/SmolLM2-135M (apache-2.0) converted to 1BP — the single-file model format used by 1bit.systems's inference engine.

1BP packs everything a loader needs into one memory-mappable file: a 256-byte header with model config, a variable-length tensor index, and Q4NX-tiled (32×256) 4-bit quantized weight data. No Python dependencies, no config files, no tokenizer files — just one file and it works.

Model Details

Property	Value
Parameters	135M
Architecture	llama
Quantization	Q4NX (4-bit, 32×256 tiles)
Source	HuggingFaceTB/SmolLM2-135M
Format	Single-file `.1bp`

Usage

# Download and run with npu_engine_universal
wget https://huggingface.co/bong-water-water-bong/SmolLM2-135M-1BP/resolve/main/SmolLM2-135M.1bp
./npu_engine_universal SmolLM2-135M.1bp 5

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bong-water-water-bong/SmolLM2-135M-1BP

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(929)

this model